STAT497 APPLIED TIME SERIES ANALYSIS

About The Course

Course Description: The course intends to meet two goals. It provides tools for empirical work with time series data and is an introduction into the theoretical foundation of time series models. Much of statistical methodology is concerned with models in which the observations are assumed to be independent. However, many data sets occur in the form of time series where observations are dependent. In this course, we will concentrate on univariate time series analysis, with a balance between theory and applications. In order to emphasize application of theory to real (or simulated) data, we will use R.

  • Name: STAT497 APPLIED TIME SERIES ANALYSIS
  • Offered By: Middle East Technical University
  • Lecturer: Prof.Dr. CEYLAN YOZGATLIGİL
  • Course website: METU Course Catalog

Skills and Insights Gained

In this course, I gained a solid foundation in both the theoretical and practical aspects of time series modeling. The course focused on univariate time series analysis, equipping me with the necessary tools for empirical analysis and strengthening my understanding of statistical methods.

Throughout the course, I explored key concepts such as Autocorrelation (ACF) and Partial Autocorrelation (PACF) plots for identifying dependencies in time series data. I also learned to perform statistical tests like the Augmented Dickey-Fuller (ADF) test, the HEGY test, and the KPSS test to check for stationarity and unit roots.

In addition to these foundational techniques, I acquired practical skills in modeling time series data using methods such as ARIMA (AutoRegressive Integrated Moving Average), SARIMA (Seasonal ARIMA), and exponential smoothing methods. These techniques allowed me to build and validate models for forecasting and analysis. The course also included hands-on experience using R to implement these models and analyze both real and simulated time series data, providing a comprehensive understanding of the field.

As part of the course, I had the opportunity to work on a project where I applied these techniques to forecast the price of Ethereum using real-life data. This project allowed me to test my knowledge and gain valuable experience in forecasting financial time series data.

If you're interested in learning more about this project and the methods used, you can follow this link to explore further.